© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 11321
    Prev
    Next
    INDEX
    Explanations

    places and organizations mentioned in a global political context

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and connecting phrases in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tains
    -0.77
    laughs
    -0.77
     Gets
    -0.75
     Kills
    -0.72
    itates
    -0.68
    izes
    -0.67
     Begins
    -0.67
    pires
    -0.66
    Written
    -0.66
    isible
    -0.65
    POSITIVE LOGITS
     are
    1.40
     were
    1.25
     aren
    1.24
     deserve
    1.17
     have
    1.13
     specialize
    1.10
     weren
    1.10
     constitute
    1.09
     comprise
    1.08
     require
    1.08
    Activations Density 0.478%

    No Known Activations